Optimize with Hyperopt¶

Home | Document

Installation¶

In [ ]:

!pip install hyperopt

!pip install hyperopt

Sample Strategy¶

In [1]:

# import talib.abstract as ta

from lettrade import DataFeed, Strategy, crossover, crossunder
from lettrade.exchange.backtest import ForexBackTestAccount, let_backtest
from lettrade.indicator.vendor.qtpylib import inject_indicators

inject_indicators()


class SmaCross(Strategy):
    ema1_period = 9
    ema2_period = 21

    def indicators(self, df: DataFeed):
        # df["ema1"] = ta.EMA(df, timeperiod=self.ema1_period)
        # df["ema2"] = ta.EMA(df, timeperiod=self.ema2_period)
        df["ema1"] = df.close.ema(window=self.ema1_period)
        df["ema2"] = df.close.ema(window=self.ema2_period)

        df["signal_ema_crossover"] = crossover(df.ema1, df.ema2)
        df["signal_ema_crossunder"] = crossunder(df.ema1, df.ema2)

    def next(self, df: DataFeed):
        if len(self.orders) > 0 or len(self.trades) > 0:
            return

        if df.l.signal_ema_crossover[-1]:
            price = df.l.close[-1]
            self.buy(size=0.1, sl=price - 0.001, tp=price + 0.001)
        elif df.l.signal_ema_crossunder[-1]:
            price = df.l.close[-1]
            self.sell(size=0.1, sl=price + 0.001, tp=price - 0.001)


lt = let_backtest(
    strategy=SmaCross,
    datas="example/data/data/EURUSD_5m_0_10000.csv",
    account=ForexBackTestAccount,
    # plotter=None,
)

# import talib.abstract as ta from lettrade import DataFeed, Strategy, crossover, crossunder from lettrade.exchange.backtest import ForexBackTestAccount, let_backtest from lettrade.indicator.vendor.qtpylib import inject_indicators inject_indicators() class SmaCross(Strategy): ema1_period = 9 ema2_period = 21 def indicators(self, df: DataFeed): # df["ema1"] = ta.EMA(df, timeperiod=self.ema1_period) # df["ema2"] = ta.EMA(df, timeperiod=self.ema2_period) df["ema1"] = df.close.ema(window=self.ema1_period) df["ema2"] = df.close.ema(window=self.ema2_period) df["signal_ema_crossover"] = crossover(df.ema1, df.ema2) df["signal_ema_crossunder"] = crossunder(df.ema1, df.ema2) def next(self, df: DataFeed): if len(self.orders) > 0 or len(self.trades) > 0: return if df.l.signal_ema_crossover[-1]: price = df.l.close[-1] self.buy(size=0.1, sl=price - 0.001, tp=price + 0.001) elif df.l.signal_ema_crossunder[-1]: price = df.l.close[-1] self.sell(size=0.1, sl=price + 0.001, tp=price - 0.001) lt = let_backtest( strategy=SmaCross, datas="example/data/data/EURUSD_5m_0_10000.csv", account=ForexBackTestAccount, # plotter=None, )

Optimize¶

In [2]:

# define a search space
from hyperopt import fmin, tpe, space_eval, Trials
from hyperopt import hp


lettrade_model = lt.optimize_model(fork_data=True)


def train_model(params):
    # Params
    params = [
        ("ema1_period", params["ema1_period"]),
        ("ema2_period", params["ema2_period"]),
    ]

    # Model
    result = lettrade_model(params)

    # Score
    return -result["equity"]


# Hyperopt
search_space = {
    "ema1_period": hp.uniform("ema1_period", 5, 25),
    "ema2_period": hp.uniform("ema2_period", 10, 50),
}

trials = Trials()
best_params = fmin(
    train_model,
    search_space,
    algo=tpe.suggest,
    max_evals=1_000,
    trials=trials,
)

# define a search space from hyperopt import fmin, tpe, space_eval, Trials from hyperopt import hp lettrade_model = lt.optimize_model(fork_data=True) def train_model(params): # Params params = [ ("ema1_period", params["ema1_period"]), ("ema2_period", params["ema2_period"]), ] # Model result = lettrade_model(params) # Score return -result["equity"] # Hyperopt search_space = { "ema1_period": hp.uniform("ema1_period", 5, 25), "ema2_period": hp.uniform("ema2_period", 10, 50), } trials = Trials() best_params = fmin( train_model, search_space, algo=tpe.suggest, max_evals=1_000, trials=trials, )

100%|██████████| 1000/1000 [03:03<00:00,  5.46trial/s, best loss: -1207.68]

In [3]:

hyperparams = space_eval(search_space, best_params)

print(best_params)
print(hyperparams)
trials

hyperparams = space_eval(search_space, best_params) print(best_params) print(hyperparams) trials

{'ema1_period': 11.053178614989243, 'ema2_period': 10.03623279848111}
{'ema1_period': 11.053178614989243, 'ema2_period': 10.03623279848111}

Out[3]:

<hyperopt.base.Trials at 0x7e2cc49564e0>

Plot¶

Tutorial

Init Plotly environment¶

In [4]:

import plotly.io as pio

pio.renderers.default = "notebook"
pio.templates.default = "plotly_dark"

import plotly.io as pio pio.renderers.default = "notebook" pio.templates.default = "plotly_dark"

In [5]:

import pandas as pd
import numpy as np


def unpack(x):
    if x:
        return x[0]
    return np.nan


# We'll first turn each trial into a series and then stack those series together as a dataframe.
df = pd.DataFrame([pd.Series(t["misc"]["vals"]).apply(unpack) for t in trials])
# Then we'll add other relevant bits of information to the correct rows and perform a couple of
# mappings for convenience
df["loss"] = [t["result"]["loss"] for t in trials]
df["trial_number"] = df.index


df["win"] = -df["loss"]
df

import pandas as pd import numpy as np def unpack(x): if x: return x[0] return np.nan # We'll first turn each trial into a series and then stack those series together as a dataframe. df = pd.DataFrame([pd.Series(t["misc"]["vals"]).apply(unpack) for t in trials]) # Then we'll add other relevant bits of information to the correct rows and perform a couple of # mappings for convenience df["loss"] = [t["result"]["loss"] for t in trials] df["trial_number"] = df.index df["win"] = -df["loss"] df

Out[5]:

	ema1_period	ema2_period	loss	trial_number	win
0	23.011308	32.392422	-874.78	0	874.78
1	12.385649	39.959152	-941.18	1	941.18
2	21.489922	13.589022	-1148.68	2	1148.68
3	24.811106	19.719090	-1029.18	3	1029.18
4	24.391799	21.758360	-1048.48	4	1048.48
...	...	...	...	...	...
995	12.980240	10.686655	-1163.58	995	1163.58
996	23.522512	13.970659	-1070.48	996	1070.48
997	14.089796	10.051155	-1163.78	997	1163.78
998	13.415534	11.662155	-1140.18	998	1140.18
999	11.819916	12.762065	-829.68	999	829.68

1000 rows × 5 columns

Type 1¶

In [6]:

from plotly import express as px

fig = px.scatter(df, x="trial_number", y="win")
fig.show()

from plotly import express as px fig = px.scatter(df, x="trial_number", y="win") fig.show()

Type 2¶

In [7]:

import plotly.express as px


fig = px.density_contour(
    df,
    x="ema1_period",
    y="ema2_period",
    z="win",
    histfunc="max",
)
fig.update_traces(contours_coloring="fill", contours_showlabels=True)
fig.show()

import plotly.express as px fig = px.density_contour( df, x="ema1_period", y="ema2_period", z="win", histfunc="max", ) fig.update_traces(contours_coloring="fill", contours_showlabels=True) fig.show()

Type 3¶

In [8]:

import plotly.express as px

fig = px.density_heatmap(
    df,
    x="ema1_period",
    y="ema2_period",
    z="win",
    nbinsx=20,
    nbinsy=40,
    histfunc="max",
    color_continuous_scale="Viridis",
)
fig.show()

import plotly.express as px fig = px.density_heatmap( df, x="ema1_period", y="ema2_period", z="win", nbinsx=20, nbinsy=40, histfunc="max", color_continuous_scale="Viridis", ) fig.show()